© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29966
    Prev
    Next
    INDEX
    Explanations

    can or should possess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     handed
    -0.10
    162
    -0.09
    iro
    -0.09
     empt
    -0.09
     impart
    -0.09
     undergo
    -0.09
    abis
    -0.09
    ugin
    -0.09
    aire
    -0.09
     remains
    -0.08
    POSITIVE LOGITS
     poss
    0.31
     облад
    0.31
     possess
    0.29
    åħ·æľī
    0.29
    poss
    0.27
     Poss
    0.27
    åħ·
    0.26
    æĭ¥æľī
    0.23
     sahip
    0.23
    Poss
    0.21
    Activations Density 0.231%

    No Known Activations